Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1190 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5986. Min Act: -0.0003

Data Index: 1026734 (C4 (Web Text))

Max Activating Token Index: 347

Text #1

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6773. Min Act: -0.0003

Data Index: 446118 (C4 (Web Text))

Max Activating Token Index: 699

Text #2

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5816. Min Act: -0.0003

Data Index: 563590 (C4 (Web Text))

Max Activating Token Index: 911

Text #3

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5950. Min Act: -0.0003

Data Index: 928740 (C4 (Web Text))

Max Activating Token Index: 962

Text #4

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6543. Min Act: -0.0003

Data Index: 865191 (C4 (Web Text))

Max Activating Token Index: 811

Text #5

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5491. Min Act: -0.0003

Data Index: 989121 (C4 (Web Text))

Max Activating Token Index: 516

Text #6

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.6020. Min Act: -0.0003

Data Index: 447691 (C4 (Web Text))

Max Activating Token Index: 417

Text #7

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5625. Min Act: -0.0003

Data Index: 932900 (C4 (Web Text))

Max Activating Token Index: 161

Text #8

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5562. Min Act: -0.0003

Data Index: 776368 (C4 (Web Text))

Max Activating Token Index: 698

Text #9

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5693. Min Act: -0.0003

Data Index: 371646 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5630. Min Act: -0.0003

Data Index: 144541 (C4 (Web Text))

Max Activating Token Index: 306

Text #11

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5264. Min Act: -0.0003

Data Index: 275991 (C4 (Web Text))

Max Activating Token Index: 431

Text #12

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5619. Min Act: -0.0003

Data Index: 236265 (C4 (Web Text))

Max Activating Token Index: 911

Text #13

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5157. Min Act: -0.0003

Data Index: 1033212 (C4 (Web Text))

Max Activating Token Index: 301

Text #14

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4848. Min Act: -0.0003

Data Index: 856014 (C4 (Web Text))

Max Activating Token Index: 573

Text #15

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5072. Min Act: -0.0003

Data Index: 441217 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5387. Min Act: -0.0003

Data Index: 461148 (C4 (Web Text))

Max Activating Token Index: 851

Text #17

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5546. Min Act: -0.0003

Data Index: 1325100 (C4 (Web Text))

Max Activating Token Index: 480

Text #18

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.5193. Min Act: -0.0003

Data Index: 1270950 (C4 (Web Text))

Max Activating Token Index: 225

Text #19

Max Range: 0.6773. Min Range: -0.6773

Max Act: 0.4834. Min Act: -0.0003

Data Index: 1092976 (C4 (Web Text))

Max Activating Token Index: 280